FACE RECOGNITION BY GREY-LEVEL CO-OCCURRENCE MATRICES IN HEXAGONAL DIGITAL IMAGE PROCESSING

Abstract

Face Recognition has been an attractive field of research fordecades, because face is one of the most useful and deterministicbiometrics. Image processing is called square pixel-based imageprocessing since its existence. However, hexagonal image processing,which is based on the idea of designing and processing pixels ashexagons, has been shown to provide significant benefits in terms of timeand memory savings. Almost all of the face recognition methods proposedand implemented so far are based on square pixel based imageprocessing. Based on the limited number of studies on face recognitionin hexagonal pixel based image processing, a hexagonal image processingbased face recognition method is proposed in this study. The methodproposed in this study is inspired by Grey Level Co-occurrence Matrices(GLCM), which is one of the most fundamental of square pixel based facerecognition methods. The method is named Hex_Direct_GLCM because itis based on the square pixel-based basic GLCM method. Since hardwarebased hexagonal pixel-based image processing is not yet available,hexagonal pixel-based equivalents of square pixel-based digital imagesare artificially created by software. The hexagonal pixel base equivalentsof the steps followed in the GLCM method are performed, and then facerecognition accuracy performance analysis is performed on different datasets. As presented in the simulation results, the Hex_Direct_GLCMmethod provides competitive results with high accuracy in terms of facerecognition as well as the success in saving resources such as time andspace.